Visual Understanding and Narration: A Deeper Understanding and Explanation of Visual Scenes

05/31/2019

∙

We describe the task of Visual Understanding and Narration, in which a robot (or agent) generates text for the images that it collects when navigating its environment, by answering open-ended questions, such as 'what happens, or might have happened, here?'

READ FULL TEXT

Visual Understanding and Narration: A Deeper Understanding and Explanation of Visual Scenes

Proposing Plausible Answers for Open-ended Visual Question Answering

Look, Read and Ask: Learning to Ask Questions by Reading Text in Images

IQA: Visual Question Answering in Interactive Environments

YouRefIt: Embodied Reference Understanding with Language and Gesture

Open-Ended Multi-Modal Relational Reason for Video Question Answering

Visual Affordance and Function Understanding: A Survey

SAMPLE-HD: Simultaneous Action and Motion Planning Learning Environment

Visual Understanding and Narration: A Deeper Understanding and Explanation of Visual Scenes

Related Research

Proposing Plausible Answers for Open-ended Visual Question Answering

Look, Read and Ask: Learning to Ask Questions by Reading Text in Images

IQA: Visual Question Answering in Interactive Environments

YouRefIt: Embodied Reference Understanding with Language and Gesture

Open-Ended Multi-Modal Relational Reason for Video Question Answering

Visual Affordance and Function Understanding: A Survey

SAMPLE-HD: Simultaneous Action and Motion Planning Learning Environment